start_date <- "2017-01-01"
end_date <- "2019-12-31"
f1<-function(d2, d1){
n_weeks <- floor(as.numeric(difftime(d2, d1, units="weeks")))
}
f2<-function(d2, d1){
n_weeks <- floor(as.numeric(difftime(as.Date(d2)
, as.Date(d1), units = "weeks")))
}
m1<-microbenchmark(
Nocast = f1(end_date, start_date),
Cast = f2(end_date, start_date),
times = 1000
)
print(m1)
## Unit: microseconds
## expr min lq mean median uq max neval
## Nocast 330.035 338.802 366.1580 343.2810 365.1665 3050.561 1000
## Cast 118.381 121.978 134.5156 123.7055 131.9560 2713.642 1000
fig <- fbox_plot(m1, "microseconds")
fig
create_c <- function (n){
x <- c()
for (i in seq(n)) {
x <- c(x, i)
}
}
create_vector <- function (n){
x <- vector("integer", n)
for (i in seq(n)) {
x[i] <- i
}
}
m3 <- microbenchmark(
with_c = create_c(1e4),
with_vector = create_vector(1e4),
times = 10
)
print(m3)
## Unit: microseconds
## expr min lq mean median uq max neval
## with_c 66038.125 66637.164 68856.0730 66846.37 67561.769 80055.678 10
## with_vector 356.465 370.431 655.7262 393.97 401.259 3091.988 10
fig <- fbox_plot(m3, "microseconds")
fig
vector <- runif(1e8)
w1 <- function(x){
d <- length(which(x > .5))
}
w2 <- function(x){
d <- sum(x > .5)
}
m4 <- microbenchmark(
which = w1(vector),
nowhich = w2(vector),
times = 10
)
print(m4)
## Unit: milliseconds
## expr min lq mean median uq max neval
## which 628.2919 631.6294 660.3250 632.9834 702.8313 768.0381 10
## nowhich 219.1176 219.5851 221.5409 220.9255 224.0479 224.5021 10
fig <- fbox_plot(m4, "miliseconds")
fig
n <- 1e4
dt <- data.table(
a = seq(n), b = runif(n)
)
v1 <- function(dt){
d <- mean(dt[dt$b > .5, ]$a)
}
v2 <- function(dt){
d <- mean(dt$a[dt$b > .5])
}
m5 <- microbenchmark(
row_operation = v1(dt),
column_operation = v2(dt),
times = 10
)
print(m5)
## Unit: microseconds
## expr min lq mean median uq max neval
## row_operation 164.467 178.844 884.7827 187.765 211.345 5125.312 10
## column_operation 63.017 68.137 283.8324 70.687 78.987 2107.412 10
fig <- fbox_plot(m5, "microseconds")
fig
The function seq prevents when the second part of the 1:x is zero
num <- 1e7
s1 <- function(num){
d <- mean(1:num)
}
s2 <- function(num){
d <- mean(seq(num))
}
m6<-microbenchmark(
noseq = s1(num),
seq = s2(num),
times = 30
)
print(m6)
## Unit: milliseconds
## expr min lq mean median uq max neval
## noseq 69.85479 69.96090 70.07312 70.01606 70.06430 71.68678 30
## seq 69.87678 69.97798 70.07228 70.02682 70.06016 71.48165 30
fig <- fbox_plot(m6, "miliseconds")
fig
large_dataset <- data.table(
id = 1:1000000,
value = sample(letters, 1000000, replace = TRUE)
)
a1 <- function(x){
d <- x %>% mutate(code = paste0(id, "_", value))
}
a2 <- function(x){
d <- x %>% mutate(code = glue("{id}_{value}"))
}
m7 <- microbenchmark(
with_paste = a1(large_dataset),
with_glue = a2(large_dataset),
times = 20
)
print(m7)
## Unit: milliseconds
## expr min lq mean median uq max neval
## with_paste 563.6145 575.2132 580.8992 578.0203 585.4943 607.3986 20
## with_glue 583.1836 589.3698 614.0820 594.8731 601.1121 965.8527 20
fig <- fbox_plot(m7, "miliseconds")
fig
# Example data
data <- data.table(group = rep(seq(10), each = 100), value = rnorm(1000))
print(table(data$group))
##
## 1 2 3 4 5 6 7 8 9 10
## 100 100 100 100 100 100 100 100 100 100
# Using a for loop
for_loop_function <- function(data) {
res <- list()
unique_groups <- unique(data$group)
for(this_group in unique_groups) {
res[[this_group]] <- data %>% filter(group == this_group)
}
return(res)
}
sapply_function <- function(data){
unique_groups <- unique(data$group)
res <- list()
sapply(unique_groups, function(this_group){
res[[this_group]] <<- data %>% filter(group == this_group)
})
return(res)
}
m8 <- microbenchmark(
for_loop = for_loop_function(data),
sapply = sapply_function(data),
times = 500
)
print(m8)
## Unit: milliseconds
## expr min lq mean median uq max neval
## for_loop 6.610062 6.758855 7.092695 6.809214 6.876074 17.75556 500
## sapply 6.714737 6.836470 7.136992 6.882496 6.945609 27.07984 500
fig <- fbox_plot(m8, "miliseconds")
fig
## Unit: microseconds
## expr min lq mean median uq max neval
## Date 1464.382 1520.521 1688.4063 1542.8235 1728.7700 3965.679 200
## iDate 572.799 600.345 681.6371 626.2235 649.5825 2402.492 200
fig <- fbox_plot(m9, "miliseconds")
fig
switch_function <- function(x) {
switch(x,
"a" = "apple",
"b" = "banana",
"c" = "cherry",
"default")
}
case_when_function <- function(x) {
case_when(
x == "a" ~ "apple",
x == "b" ~ "banana",
x == "c" ~ "cherry",
TRUE ~ "default"
)
}
# Create a vector of test values
test_values <- sample(c("a", "b", "c", "d"), 1000, replace = TRUE)
m10 <- microbenchmark(
switch = sapply(test_values, switch_function),
case_when = sapply(test_values, case_when_function),
times = 200L
)
print(m10)
## Unit: microseconds
## expr min lq mean median uq max
## switch 633.452 641.156 747.4343 647.8485 663.5075 9520.652
## case_when 223495.741 232348.918 235780.3888 235294.2830 236867.4930 327207.864
## neval
## 200
## 200
fig <- fbox_plot(m10, "microseconds")
fig
set.seed(123)
n <- 1e6
data <- data.table(
id = seq(n),
value = sample(seq(100), n, replace = TRUE)
)
casewhenf <- function(data){
df <- data %>%
mutate(category = case_when(
value <= 20 ~ "Low",
value <= 70 ~ "Medium",
value > 70 ~ "High"))
}
fcasef <- function(data){
df <- data %>%
mutate(category = fcase(
value <= 20, "Low",
value <= 70, "Medium",
value > 70, "High"))
}
m11 <- microbenchmark(
case_when = casewhenf(data),
fcase = fcasef(data),
times = 20
)
print(m11)
## Unit: milliseconds
## expr min lq mean median uq max neval
## case_when 56.48162 56.75932 60.64567 56.91790 64.56608 75.87161 20
## fcase 20.58373 20.73047 21.54201 20.78755 20.91723 26.75514 20
fig <- fbox_plot(m11, "miliseconds")
fig
set.seed(123)
DT <- data.table(
ID = 1:1e6,
Value1 = sample(c(NA, 1:100), 1e6, replace = TRUE),
Value2 = sample(c(NA, 101:200), 1e6, replace = TRUE)
)
# Define the functions
replace_na_f <- function(data){
DF <- data %>%
mutate(Value1 = replace_na(Value1, 0),
Value2 = replace_na(Value2, 0)) %>%
as.data.table()
}
fcoalesce_f <- function(data){
DF <- data %>%
mutate(Value1 = fcoalesce(Value1, 0L),
Value2 = fcoalesce(Value2, 0L))
}
m12 <- microbenchmark(
treplace_na = replace_na_f(DT),
tfcoalesce = fcoalesce_f(DT),
times = 20
)
print(m12)
## Unit: milliseconds
## expr min lq mean median uq max neval
## treplace_na 7.400617 7.745105 14.606019 7.893111 9.481610 80.23419 20
## tfcoalesce 1.517451 1.703418 6.492432 1.897015 2.700749 62.61303 20
fig <- fbox_plot(m12, "miliseconds")
fig
dt <- data.table(field_name = c("argentina.blue.man.watch",
"brazil.red.woman.shoes",
"canada.green.kid.hat",
"denmark.red.man.shirt"))
# Filter rows where 'field_name' does not contain 'red'
dtnot <- function(data){
filtered_dt <- data |> _[!grepl("red", field_name)]
}
dplyrnot <- function(data){
filtered_dt <- data %>% filter(!grepl("red", field_name))
}
m13 <- microbenchmark(
tdtnot = dtnot(dt),
tdplyrnot = dplyrnot(dt),
times = 100
)
print(m13)
## Unit: microseconds
## expr min lq mean median uq max neval
## tdtnot 100.478 109.474 142.8368 129.1915 138.2230 1806.06 100
## tdplyrnot 666.544 686.541 726.1847 698.1730 716.7525 2728.61 100
fig <- fbox_plot(m13, "microseconds")
fig
large_data <- data.table(
id = 1:100000,
var1 = rnorm(100000),
var2 = rnorm(100000),
var3 = rnorm(100000),
var4 = rnorm(100000)
)
# Benchmarking
m14 <- microbenchmark(
tidyr_pivot_longer = {
long_data_tidyr <- pivot_longer(large_data, cols = starts_with("var"),
names_to = "variable", values_to = "value")
},
data_table_melt = {
long_data_dt <- melt(large_data, id.vars = "id", variable.name = "variable",
value.name = "value")
},
times = 10
)
print(m14)
## Unit: microseconds
## expr min lq mean median uq max
## tidyr_pivot_longer 6143.391 6216.117 7734.5541 6279.240 6361.909 20979.150
## data_table_melt 464.346 497.208 566.4518 529.207 593.286 760.268
## neval
## 10
## 10
fig <- fbox_plot(m14, "microseconds")
fig